Mentors of the Summer School "Coding for Language Communities"

Kevin Scannell

About Kevin

Kevin Scannell is Professor of Mathematics and Computer Science at Saint Louis University in the USA. He works with endangered language groups around the world to develop basic computing resources like online dictionaries, spell checkers, software localizations, and keyboard input methods. He founded the Indigenous Tweets project in March 2011 to promote the use of indigenous and minority languages in social media.

Project during the Summer School

Kevin's team will turn corpus data into spellcheckers. You will learn how to crawl, clean and tokenize data from the web, then generate frequency lists, add morphology, all the way to packaging up Firefox/OpenOffice extensions.

Bruce Birch

About Bruce

Bruce Birch is a linguist specializing in languages of the Iwaidjan family spoken in the Cobourg region of Northwestern Arnhem Land in the north of Australia. Since 2003 he has been documenting endangered areas of knowledge in these languages including ecology, kinship and social organization, and oral history. Over the same period he has been a coordinator of Iwaidja Inyman (Iwaidja Language), a government-funded publishing project now producing some of the world’s first crowdsourcing software for the documentation of endangered languages under the rubric of the Ma! Project. This project is currently producing Android and iOS based crowdsourcing lexicon development smartphone and tablet apps for a number of languages around the world including Iwaidja (Australia), Mokpe (Cameroon), Bena Bena (PNG), Gamilaraay (Australia), and Somali, as well as an interpreting app for the Aboriginal Interpreter Service in Darwin, Australia.

Project during the Summer School

Bruce's team will work on a mobile app for crowdsourced data collection and publishing. Among his ideas are apps for lexical data, phrasebooks, stories and other data from endangered languages. You will learn how to develop a database for the content and how to enable users to edit and share their content.

Dorothee Beermann

About Dorothee

Dorothee Beermann is an assoc. professor at the Department for Language and Literature at the Norwegian University of Science and Technology in Trondheim, Norway.  A formal syntactican from training, she is a linguist gone tool developer. Her tool is TypeCraft, an online service for the creation and management of Interlinear Glossed Text, IGT, which is the most common data format in the descriptive and theoretical fields of linguistics.

Peter Grasch

About Peter

Peter Grasch is a co-founder and current maintainer of the open source speech recognition system Simon. He has been involved in building and deploying speech recognition systems in areas as diverse as voice controlled multimedia systems for people with speech impediments to caregiving robots for elderly people. Peter recently founded the Open Speech Initiative and is currently working towards a truly open speech recognition system capable of large
vocabulary dictation.

Project during the Summer School

Peter's team will learn how to craft custom speech recognition systems tailored specifically for a given task, language or dialect, using only open and freely available software.

Peter Bouda

About Peter

Peter is a co-founder of CIDLeS and the head of the CIDLeS Media Lab. He is responsible for the development of Poio, a predictive text system for under-resourced languages. He represents CIDLeS in the "Working Group 3: Linguistic Fieldwork, Anthropology, Language Typology" of the CLARIN framework programme.

He is also a researcher at the University of Marburg, within the project Quantitative Historical Linguistics. The project aims to uncover and clarify phylogenetic relationships between native South American languages using quantitative methods. The two main objectives of the projects are digitalization of the lexical resources on native South American languages and development of new and innovative computer-assisted methods to quantitatively analyze this information.

Peter is a big fan of LEGO® and won the Codebits Coding Competition in Lisbon in 2011 with a project called "LEGO® Coding", where he used Lego bricks as commands in a physical programming language. He occasionally acts as a judge at the FIRST® LEGO® League Portugal.

See the programme >>>